Skip to content

gliclass-v4:2b

3 TagsUpdated 2.4B params8192 contextEnglishApache-2.0by Knowledgator

gliclass-v4-2b (decoder-KV on Qwen3.5-2B, 2.4B weights read), fp32 compute on BF16 weights: about 7 GB in memory.

2.4b
ollaya run gliclass-v4:2b --preset triage "I was charged twice for my subscription this month and want a refund."

Details

  • graphcce70796f1a8 · 12 MBonnx · gliclass-kv · 2.4B · fp32
  • weights8b8308376488 · 4.7 GBhuggingface.co/knowledgator/gliclass-v4-2b/resolve/40fe023…/model.safetensors
  • tokenizer04472e9fcd4a · 20 MBhuggingface.co/knowledgator/gliclass-v4-2b/resolve/40fe023…/tokenizer.json
  • decision422d5d5104c9 · 3 KB{"engine": "onnx", "family": "gliclass-kv", "encoder": "", "layout": "gliclass-kv-v1", …}
  • calibrationadff5b1a2745 · 177 B{"temperature": [1.0, 1.0, 1.0]}
  • license94fbb5a513de · 10 KBGLiClass v4 by Knowledgator (https://huggingface.co/knowledgator/gliclass-v4-2b, https://huggingface.co/knowledgator/gliclass-v4-9b)

Every layer is checked against its sha256 when it is pulled. Weights and tokenizers download from the model author's Hugging Face repository at a pinned commit; Ollaya never re-hosts them.

GLiClass v4 readme and all models